Detection of ventricular fibrillation using empirical mode decomposition and Bayes decision theory

Ventricular fibrillation (VF) is the most serious variety of arrhythmia which requires quick and accurate detection to save lives. In this paper, we propose an empirical mode decomposition (EMD) based algorithm for VF detection. The intrinsic mode functions (IMFs) of VF are orthogonal whereas the lower order IMFs of normal sinus rhythm (NSR) are not. The orthogonality indices derived from the first three consecutive intrinsic mode functions (IMFs) of NSR and VF are used for their discrimination. The proposed technique is applied to the MIT-BIH arrhythmia database. The accuracy of detection of VF is 99.70% for a window length of 3s. This early estimate of VF may be useful in emergency cases where defibrillators are to be applied. Comparative results with the existing methods in terms of quality parameters and integrated receiver operating characteristic (IROC) are presented.